detect_small.py

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

import argparse
import os
import sys
from pathlib import Path

import torch
import torch.backends.cudnn as cudnn
import time

FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative

from models.common import DetectMultiBackend
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                           increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh,
                           apply_classifier)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync



@torch.no_grad()
def run(
        weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
        source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcam
        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
        imgsz=(640, 640),  # inference size (height, width)
        conf_thres=0.25,  # confidence threshold
        iou_thres=0.45,  # NMS IOU threshold
        max_det=1000,  # maximum detections per image
        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        view_img=False,  # show results
        save_txt=False,  # save results to *.txt
        save_conf=False,  # save confidences in --save-txt labels
        save_crop=False,  # save cropped prediction boxes
        nosave=False,  # do not save images/videos
        classes=None,  # filter by class: --class 0, or --class 0 2 3
        agnostic_nms=False,  # class-agnostic NMS
        augment=False,  # augmented inference
        visualize=False,  # visualize features
        update=False,  # update all models
        project=ROOT / 'runs/detect',  # save results to project/name
        name='exp',  # save results to project/name
        exist_ok=False,  # existing project/name ok, do not increment
        line_thickness=3,  # bounding box thickness (pixels)
        hide_labels=False,  # hide labels
        hide_conf=False,  # hide confidences
        half=False,  # use FP16 half-precision inference
        dnn=False,  # use OpenCV DNN for ONNX inference
):
    source = str(source)
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    if is_url and is_file:
        source = check_file(source)  # download

    # Directories
    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Load model
    device = select_device(device)
    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
    stride, names, pt = model.stride, model.names, model.pt
    imgsz = check_img_size(imgsz, s=stride)  # check image size

    # Dataloader
    if webcam:
        view_img = check_imshow()
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
        bs = len(dataset)  # batch_size
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
        bs = 1  # batch_size


    # Run inference
    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
    seen, windows, dt = 0, [], [0.0, 0.0, 0.0]
    t0 = time.time()
    dtlast = 0
    temp_prediction = 0
    a = False
    box_temp = [0, 0, 0, 0]
    for path, im, im0s, vid_cap, s in dataset:
        print(im.shape)
        t1 = time_sync()
        im = torch.from_numpy(im).to(device)
        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
        im /= 255  # 0 - 255 to 0.0 - 1.0
        if len(im.shape) == 3:
            im = im[None]  # expand for batch dim
        t2 = time_sync()
        dt[0] += t2 - t1

        # Inference
        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False

        pred = model(im, augment=augment, visualize=visualize)
        t3 = time_sync()
        print('%.2f'%float(1/(t3 - t2)))
        dt[1] += t3 - t2

        # # NMS 防止抖动
        # if a:
        #     pre_predic = temp_prediction
        #     temp_prediction = pred[..., 4]
        # else:
        #     pre_predic = 0
        #     a = True
        #     temp_prediction = pred[..., 4]
        #
        # pred[..., 4] += pre_predic * 0.5
        # # 对本帧的预测结果叠加一个上一帧的权重，目前权重设置为0.5，取决于不同任务，建议设置值在0.05~0.5之间

        # NMS
        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
        dt[2] += time_sync() - t3

        # Second-stage classifier (optional)
        # pred = apply_classifier(pred, classifier_model, im, im0s)

        # Process predictions
        for i, det in enumerate(pred):  # per image

            seen += 1
            if webcam:  # batch_size >= 1
                p, im0, frame = path[i], im0s[i].copy(), dataset.count
                s += f'{i}: '
            else:
                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            s += '%gx%g ' % im.shape[2:]  # print string
            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string


                # cv2.putText(im0, f"{n} {names[int(c)]}{'s' * (n > 1)}", (20, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.2,
                #             (0, 0, 255), 2)

                # Write results
                for *xyxy, conf, cls in reversed(det):

                    x1 = int(xyxy[0].item())
                    y1 = int(xyxy[1].item())
                    x2 = int(xyxy[2].item())
                    y2 = int(xyxy[3].item())
                    box = [x1, y1, x2, y2]
                    if  view_img:  # Add bbox to image
                        iou = cal_iou_xyxy(box, box_temp)
                        if iou > 0.95:
                            xyxy = label_temp
                        else:
                            label_temp = xyxy
                            box_temp = box
                        c = int(cls)  # integer class
                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
                        annotator.box_label(xyxy, label, color=colors(c, True))
            fp = int(1 / (time_sync() - dtlast))
            dtlast = time_sync()
            cv2.putText(im0, f"{len(det)}", (20, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 2)
            # Stream results
            im0 = annotator.result()
            if view_img:

                # 增加显示FPS

                cv2.putText(im0, f"{fp}", (20, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.2,(0, 0, 255), 2)

                cv2.imshow(str(p), im0)
                cv2.waitKey(0)  # 1 millisecond

        # Print time (inference-only)
        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)**********')

    # Print results
    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
    t_all = tuple(int(x)  for x in dt)
    print(t_all)
    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
    if save_txt or save_img:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
    print(f'Done. ({time.time() - t0:.3f}s)')
    if update:
        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)
def cal_iou_xyxy(box1,box2):
    x1min, y1min, x1max, y1max = box1[0], box1[1], box1[2], box1[3]
    x2min, y2min, x2max, y2max = box2[0], box2[1], box2[2], box2[3]
    #计算两个框的面积
    s1 = (y1max - y1min + 1.) * (x1max - x1min + 1.)
    s2 = (y2max - y2min + 1.) * (x2max - x2min + 1.)

    #计算相交部分的坐标
    xmin = max(x1min,x2min)
    ymin = max(y1min,y2min)
    xmax = min(x1max,x2max)
    ymax = min(y1max,y2max)

    inter_h = max(ymax - ymin + 1, 0)
    inter_w = max(xmax - xmin + 1, 0)

    intersection = inter_h * inter_w
    union = s1 + s2 - intersection

    #计算iou
    iou = intersection / union
    return iou

def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / r'weights/person.pt', help='model path(s)')
    parser.add_argument('--source', type=str, default=ROOT / r'data/images', help='file/dir/URL/glob, 0 for webcam')
    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
    parser.add_argument('--conf-thres', type=float, default=0.3, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.5, help='NMS IoU threshold')
    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img',default=True,action='store_true', help='show results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
    parser.add_argument('--nosave', default=True,action='store_true', help='do not save images/videos')
    parser.add_argument('--classes', default=0,nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--visualize', action='store_true', help='visualize features')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
    parser.add_argument('--name', default='exp', help='save results to project/name')
    parser.add_argument('--exist-ok',default=True, action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
    opt = parser.parse_args()
    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
    print_args(vars(opt))
    return opt


def main(opt):
    check_requirements(exclude=('tensorboard', 'thop'))
    run(**vars(opt))


if __name__ == "__main__":
    opt = parse_opt()

    main(opt)